Serena Ge
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Software Eng.×1ML×1
Frequent co-authors
Research Timeline
2026
DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks
DeepSWE is a new benchmark for evaluating coding agents with original tasks written from scratch and hand-graded verifiers.
Highlighted terms show continued research focus across papers